List your company

Functional Correctness on CPP-Bench

38.1Functional Success Rate @1IG-CD
14.80420.85226.932.948Jan 31, 2026

Evaluation results

MethodLinks
IG-CDBackbone Model=DiffuC-7B, Decoding Method=IG-CD2026.0138.138.338.338.5
LAVEBackbone Model=DiffuC-7B, Decoding Method=LAVE2026.0138.138.438.538.5
NO-CDBackbone Model=DiffuC-7B, Decoding Method=NO-CD2026.0137.237.437.837.8
FS-CDBackbone Model=DiffuC-7B, Decoding Method=FS-CD2026.0135.235.535.835.9
LAVEBackbone Model=Dream-7B, Decoding Method=LAVE2026.0133.538.239.541.4
IG-CDBackbone Model=Dream-7B, Decoding Method=IG-CD2026.0129.130.530.831.1
FS-CDBackbone Model=Dream-7B, Decoding Method=FS-CD2026.0126.526.827.127.5
NO-CDBackbone Model=Dream-7B, Decoding Method=NO-CD2026.0125.626.226.828.1
LAVEBackbone Model=LLaDA-8B, Decoding Method=LAVE2026.0119.523.825.926.7
LAVEBackbone Model=LLaDA-1.5, Decoding Method=LAVE2026.0119.12324.928.8
IG-CDBackbone Model=LLaDA-1.5, Decoding Method=IG-CD2026.0118.321.323.127.1
IG-CDBackbone Model=LLaDA-8B, Decoding Method=IG-CD2026.0117.822.523.725.6
NO-CDBackbone Model=LLaDA-1.5, Decoding Method=NO-CD2026.0117.220.12225.9
NO-CDBackbone Model=LLaDA-8B, Decoding Method=NO-CD2026.0116.321.823.124.9
FS-CDBackbone Model=LLaDA-1.5, Decoding Method=FS-CD2026.0115.916.116.516.5
FS-CDBackbone Model=LLaDA-8B, Decoding Method=FS-CD2026.0115.7161616.2